Maze Mouse Annotated Pose Dataset
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This Zenodo repository includes the annotation data for a mouse in a maze dataset. The two keypoints on the mouse that are tracked are: "nose" and "butt" (also known as tail-base). There are also bounding boxes around the mouse that can be used for top-down pose estimation model training. Next, we include annotation data for the maze corners that we used in our internal processing. It is unlikely that someone else will need that data, but we have provided it for the sake of completeness. Folder structure maze-annotations/ annotations/ The annotation files for the mouse in maze annotations images/ Location of all of the images for this training and testing dataset vis/ visual examples of keypoints and bounding boxes of the mouse overlaid over images. Not necessary for training. maze_corners/ Training data for training maze corners. Unlikely that others will want to use this training set but includes same file structure as the mouse maze anntoations. annotations/ The annotation files for the maze corner annotations images/ Location of all the images for this training and testing dataset vis/ visual examples of keypoints and bounding boxes of the maze corners overlaid over images. Not necessary for training.
Fields of Study & Subjects
Human Pose and Action Recognition
Advanced Neural Network Applications
Video Surveillance and Tracking Methods
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 24 March 2026
- Language
- EN
- Document type
- Dataset